About this Abstract |
Meeting |
2025 TMS Annual Meeting & Exhibition
|
Symposium
|
Additive Manufacturing Modeling, Simulation and Machine Learning
|
Presentation Title |
Prediction of Thermal Profile of Heat-Affected Zone during Laser Cladding from a Long-Wavelength Infrared Camera |
Author(s) |
Sang-Hum Kwon, Dae-Geun Hong, Dong-Won Lee, Chang-Hee Yim, Nam-Kyu Park, Deok-Su Yun, Tae-Gyu Lee, Rae-Hyung Chung |
On-Site Speaker (Planned) |
Dae-Geun Hong |
Abstract Scope |
During the laser cladding (LC) process, a heat-affected zone (HAZ) heats and cools rapidly, and the rapid temperature changes causes thermal deformation, which can lead to formation of pores and cracks. So, quantitative analysis of the HAZ is necessary for quality control of the LC coated product. In this study, thermal profile image prediction on laser-cladding behavior were conducted based on a deep learning method by using data collected from a long-wavelength infrared camera. The changing HAZ behavior during the LC process was photographed using thermal imaging cameras to quantify the temperature distribution, the HAZ behavior over time, and overlap of successive layers. The results showed that the proposed model accurately predicted the thermal profile of the HAZ, so that quantitative information of the HAZ such as the temperature distribution, the maximum temperature, and whether it is overheated could be judged in advance. |
Proceedings Inclusion? |
Planned: |
Keywords |
Additive Manufacturing, Machine Learning, Modeling and Simulation |